Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and complex reasoning tasks.
Author
AlibabaRelease Date
2026-04-27
Knowledge Cutoff
—
License
Proprietary
I/O Format
Context Length
262K / 66K
API I/O (1M)
$1.04 / $6.24
How to Use
—
Output Speed
47 tok/sArena Overall
1457Intelligence Index
51.8Coding Index
44.9Math Index
—LiveBench
—ForecastBench
—GPQA Diamond
88.8%HLE
28.9%MMLU-Pro
—AIME 2025
—MATH-500
—LB Reasoning
—LB Math
—LB Data Analysis
—LiveCodeBench
—LB Coding
—LB Agentic
—TAU2
95.9%TerminalBench
43.9%SciCode
46.9%IFBench
76.6%AA-LCR
0.7Hallucination (HHEM)
—Factual Consistency (HHEM)
—LB Language
—LB Instruction Following
—1 / 3
Swipe to compare
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and complex reasoning tasks.
Author
AlibabaRelease Date
2026-04-27
Knowledge Cutoff
—
License
Proprietary
I/O Format
Context Length
262K / 66K
API I/O (1M)
$1.04 / $6.24
How to Use
—
Output Speed
47 tok/sArena Overall
1457Intelligence Index
51.8Coding Index
44.9Math Index
—LiveBench
—ForecastBench
—GPQA Diamond
88.8%HLE
28.9%MMLU-Pro
—AIME 2025
—MATH-500
—LB Reasoning
—LB Math
—LB Data Analysis
—LiveCodeBench
—LB Coding
—LB Agentic
—TAU2
95.9%TerminalBench
43.9%SciCode
46.9%IFBench
76.6%AA-LCR
0.7Hallucination (HHEM)
—Factual Consistency (HHEM)
—LB Language
—LB Instruction Following
—